Aditya Dhodapkar
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Crypto×1AI×1
Frequent co-authors
Research Timeline
2026
SafetyDrift: Predicting When AI Agents Cross the Line Before They Actually Do
The paper introduces SafetyDrift, a predictive model that forecasts when AI agents will violate safety protocols by analyzing the cumulative risk across sequences of individually safe actions.
Highlighted terms show continued research focus across papers